© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 7001
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that start with "If you" and end with a statement or question, possibly related to technology or lifestyle choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate familiarity or connection with the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bravo
    -0.70
     Pir
    -0.66
     scattering
    -0.66
    onite
    -0.64
     Folk
    -0.62
     DNA
    -0.60
     doubtless
    -0.59
     shifting
    -0.59
     dwindling
    -0.59
     secondary
    -0.58
    POSITIVE LOGITS
    agree
    1.09
    want
    1.09
    were
    0.98
    didn
    0.96
    someone
    0.96
    felt
    0.95
    treated
    0.94
    true
    0.93
    operated
    0.91
    ever
    0.91
    Activations Density 0.124%

    No Known Activations